To search, Click below search items.


All Published Papers Search Service


Comparison of Reinforcement and Supervised Learning Algorithms on Startup Success Prediction


Yong Shi, Eremina Ekaterina, Wen Long


Vol. 20  No. 7  pp. 86-97


There has been an exponential growth in startups over the past few years. More than half of startups fail to gain funding. Predicting the success of a startup allows investors to find companies that have the potential for rapid growth, thereby allowing them to be one step ahead of competition. This paper proposes implementing a model to predict whether startup will be a failure or succeed based on many important factors like idea of the startup, place where the startup established, domain vertical to which the startup belongs, type of funding. On the preprocessed data we used several classification techniques along with data mining optimizations and validations. We provide our analysis using techniques such as Random Forest, KNN, Bayesian Networks, and so on. We evaluate the correctness of our models based on factors precision and recall. Our model can be used by startup to decide on what factors they should focus in order to succeed. Also this work aims to compare efficiency of supervised machine learning algorithms and reinforcement learning algorithms for multi-labeled classification task. Adaptations of successful multi-armed bandits policies to the online contextual bandits scenario with binary rewards using binary classification algorithms is also explored.


CrunchBase, multi-class classification, contextual bandits, supervised machine learning